Research map / Image generation / Super-resolution
NeurOp-Diff: Continuous Remote Sensing Image Super-Resolution via Neural Operator Diffusion
Zihao Xu, Yuzhi Tang, Bowen Xu, Qingquan Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| condition diffusion on neural-operator-encoded LR features instead of bicubic-upsampled LR (ablation) | NeurOp-Diff · UCMerced 4x SR | PSNR: 27.15 -> 28.14 | Improved |
| condition diffusion on neural-operator-encoded LR features instead of bicubic-upsampled LR (ablation) | NeurOp-Diff · UCMerced 4x SR | SSIM: 0.7587 -> 0.7761 | Improved |
| condition on neural-operator features instead of EDSR-encoded LR features (ablation) | NeurOp-Diff · UCMerced 4x SR | PSNR: 27.42 -> 28.14 | Improved |
| condition on neural-operator features instead of EDSR-encoded LR features (ablation) | NeurOp-Diff · UCMerced 4x SR | SSIM: 0.7602 -> 0.7761 | Improved |
| NeurOp-Diff vs SR3 baseline at 8x | SR3 · UCMerced 8x SR | PSNR: 23.12 -> 24.51 | Improved |
| NeurOp-Diff vs best generative baseline TCDM at 4x | TCDM · AID 4x SR | PSNR: 27.53 -> 27.57 | No clear effect |
| NeurOp-Diff vs TCDM at 4x | TCDM · UCMerced 4x SR | PSNR: 27.83 -> 28.14 | Improved |
| NeurOp-Diff vs IDM in inference time at T=50 | IDM · Inference time per image | seconds: 1.79 -> 1.52 | Improved |
| NeurOp-Diff vs SR3 inference time at T=100 | SR3 · Inference time per image | seconds: 3.23 -> 2.61 | Improved |
| NeurOp-Diff vs regression SRNO at 4x | SRNO · UCMerced 4x SR | PSNR: 29.21 -> 28.14 | Hurt |
| NeurOp-Diff vs regression SRNO at 4x | SRNO · UCMerced 4x SR | LPIPS: 0.164 -> 0.136 | Improved |
| NeurOp-Diff vs SRNO at out-of-distribution 10x | SRNO · UCMerced continuous SR 10x | SSIM: 0.592 -> 0.633 | Improved |
Closest papers by meaning
- Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model (CVPR 2024 · similarity 0.89)
- DiffFNO: Diffusion Fourier Neural Operator (CVPR 2025 · similarity 0.88)
- SinSR: Diffusion-Based Image Super-Resolution in a Single Step (CVPR 2024 · similarity 0.87)
- ResDiff: Combining CNN and Diffusion Model for Image Super-resolution (AAAI 2024 · similarity 0.87)
- Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decoder (CVPR 2024 · similarity 0.87)
- Noise-Free Optimization in Early Training Steps for Image Super-resolution (AAAI 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
